CN111273607A - Spark-based numerical control machine tool running state monitoring method - Google Patents
Spark-based numerical control machine tool running state monitoring method Download PDFInfo
- Publication number
- CN111273607A CN111273607A CN201811472641.1A CN201811472641A CN111273607A CN 111273607 A CN111273607 A CN 111273607A CN 201811472641 A CN201811472641 A CN 201811472641A CN 111273607 A CN111273607 A CN 111273607A
- Authority
- CN
- China
- Prior art keywords
- data
- spark
- machine tool
- numerical control
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/45—Nc applications
- G05B2219/45136—Turning, lathe
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to a Spark-based numerical control machine tool running state monitoring method.A system takes Apache Spark as a basic computing frame, thereby realizing the processing and analysis of mass running data, and simultaneously adding an acquisition module based on an OPC protocol, a Kafka distributed message queue and other components to provide a reliable data interface for the system. And discovering data distribution characteristics, namely different health states, in different time periods by adopting a density clustering-based DBSCAN algorithm on the historical data through Spark-MLib. Meanwhile, an SVM classification algorithm is adopted to establish a monitoring model, so that the real-time monitoring of the safe operation state of the numerical control machine tool is realized.
Description
Technical Field
The invention relates to the field of numerical control systems, digital workshops and intelligent manufacturing, in particular to a Spark-based numerical control machine running state monitoring system realized under a Windows platform.
Background
With the development of information technology, the traditional machine manufacturing industry starts to revolutionarily change by the characteristics of informatization and intellectualization, the machine manufacturing industry gradually enters the era of industrial big data, and Germany 'industry 4.0', American 'industrial internet' and 'Chinese manufacture 2025' all propose to utilize the internet and big data thinking to improve the intellectualization level of the manufacturing industry and comprehensively improve the overall efficiency of the manufacturing industry.
Meanwhile, many enterprises form numerically-controlled machine tool workshops of considerable scale, data generated in the operation process of equipment is increased in geometric progression, traditional numerically-controlled machine tool maintenance mainly adopts a manual regular inspection mode, the efficiency is extremely low, the traditional numerically-controlled machine tool maintenance completely depends on professional quality of machine tool maintenance personnel, the maintenance personnel cannot be warned in advance, meanwhile, massive machining process data are regarded as garbage data to be discarded, and serious data resource waste is caused, although the applications of intelligent monitoring, Internet of things monitoring and the like are continuously promoted in the numerical control field, when the large amount of data are faced, theoretical system research of storage and model construction is mainly focused, data analysis cannot be carried out by combining with an actual application framework, and therefore a monitoring system based on a large data platform needs to be constructed in time to effectively process and analyze various data in the machining process of a machine tool, the real-time monitoring and early warning of the running state of the numerical control machine tool are realized.
Disclosure of Invention
Aiming at the defects in the prior art, the Spark high-performance parallel computing engine quasi-real-time performance and high throughput are combined, and the technical problem to be solved by the invention is to provide a Spark-based numerical control machine running state monitoring system for monitoring and managing the real-time state of a numerical control machine.
The technical scheme adopted by the invention for realizing the purpose is as follows: a Spark-based numerical control machine tool running state monitoring system comprises the following steps:
step 1: collecting state data information of the numerical control machine tool;
step 2: then, carrying out normalization processing on the state data information to obtain state data;
and step 3: kafka accesses state data, different types of state data are integrated by adding a Topic field into the data, the data of the same Topic are partitioned to different servers according to a set algorithm, and a stream computing system spark streaming computes the data;
and 4, step 4: preprocessing the state data by using Spark streaming of Spark to obtain a state data sample;
and 5: taking a state data sample as input, dividing a monitored object into different safety states as output, and establishing a multi-classification prediction model; and predicting the monitoring data to be detected through a multi-classification prediction model.
The acquisition is realized in one of two ways; the first mode is through the development interface of the numerical control machine tool, and the other mode is through the OPC protocol acquisition.
The state data information comprises spindle motor temperature, spindle current, spindle motor load, spindle rotation error, X-axis motor temperature and feeding speed.
The preprocessing of the state data by using Spark streaming is specifically as follows:
in Spark Job of Spark, data of each Topic in Kafka is defined as a data stream DStream, and each DStream is internally represented by a set of consecutive RDDs.
The method for establishing the multi-classification prediction model by using the state data samples as input and the monitoring objects divided into different safety states as output comprises the following steps:
clustering data generated in different time periods in a data set into different clusters by training labeled state data samples and using a density-based clustering algorithm DBSCAN, thereby finding different safe operation states of a machine tool, and dividing a monitored object into different safe states according to a clustering result;
and establishing a multi-classification prediction model by adopting an SVM classification algorithm aiming at different safety states.
The clustering algorithm DBSCAN based on density is as follows:
1) classifying core points, boundary points and noise points according to the density based on the center: if the number of points contained in the neighborhood with the epsilon as the radius of the point o exceeds a given threshold value MinPts, the point o is marked as a core point; points which are not core points but fall in the neighborhood of a certain core point are marked as boundary points; any point that is neither a core point nor a boundary point is a noise point;
2) deleting all noise points;
3) connecting two core points with the distance smaller than the neighborhood radius epsilon to form a new cluster;
4) the recorded data at each moment is given a cluster class label, namely corresponding to a safety state of the monitored object.
The method for establishing the multi-classification prediction model by adopting the SVM classification algorithm comprises the following steps:
and for the data corresponding to each class label, marking the points belonging to the class as positive examples, marking the points not belonging to the class as negative examples, and training a classifier for the class by using the marked data through an SVM algorithm.
The prediction of the monitoring data to be detected through the multi-classification prediction model is as follows: classifying the newly generated monitoring data by using a classifier corresponding to each safety state respectively, integrating classification results of all the classifiers, and judging the safety state of the monitoring data to be the class when one and only one classifier divides the monitoring data into the corresponding states; otherwise, if there is no classifier or the classifiers classify the data into the corresponding states, the safety state of the monitored data is determined as the outlier.
The invention has the following beneficial effects and advantages:
1. and (4) economy. Aiming at different data processing occasions, programming modes based on Spark are unified into the same processing mode, Spark unifies a technical stack, and research and development cost is reduced.
2. And (4) real-time performance. The invention is based on Spark framework, so that the invention has quasi-real-time performance and higher throughput.
3. And (4) intelligent early warning. The state of the component is preliminarily identified by comparing the monitoring state information and the characteristic parameters with normal values, and the health state of the component is predicted by establishing a health state model based on a time sequence to achieve the aim of early warning.
Drawings
FIG. 1 is a block diagram of the system of the present invention;
FIG. 2 is a block diagram of a data acquisition and access module according to the present invention;
fig. 3 is a flow chart of Spark Streaming operation according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in fig. 1 to 2, a system for monitoring the running state of a numerically-controlled machine tool based on Spark comprises the following steps:
step 1: the method comprises the following steps of collecting state data information of the numerical control machine tool, wherein the first mode is a development interface provided by a numerical control manufacturer, and the other mode is to obtain the running state data of the numerical control machine tool in an OPC protocol mode;
step 2: then, carrying out normalization processing on the original sample parameters by adopting a z-score normalization method;
and step 3: and the access to the state data is realized by introducing a distributed message queue Kafka. And realizing the integrated sending of different types of state data by adding the data into the Topic field. I.e. messages within the same topoc are partitioned to different servers according to a certain algorithm. When issuing information, the stream data generation system distributes the data stream to the Kafka message subject as a producer of the Kafka message data, and the stream calculation system SparkStreaming consumes and calculates the data in real time.
And 4, step 4: preprocessing the implementation state monitoring data by using a Spark streaming real-time data calculation framework of Spark, namely defining continuous data sources of each Topic in Kafka as a data stream DStream in Spark Job, wherein each DStream is internally represented by a group of continuous RDDs, and then converting the operation of the DStream into the operation of the RDDs in Spark; as shown in fig. 3.
And 5: the method comprises the steps of establishing an operation state monitoring model by combining actual characteristics of machine tool parameters and using six parameters of spindle motor temperature, spindle current, spindle motor load, spindle rotation error, X-axis motor temperature and feed speed, clustering data generated in different time periods in a data set into different clusters by using a density-based clustering algorithm DBSCAN through training labeled parameter samples, finding different safe operation states of the machine tool, and dividing a monitored object into different safe states according to a clustering result. And establishing a multi-classification prediction model by adopting an SVM classification algorithm aiming at different safety states, and realizing the prediction of the health state of monitoring data generated in the future.
The clustering algorithm DBSCAN based on density is as follows:
step 1: and classifying the core points, the boundary points and the noise points according to the density based on the center. If the number of points contained in the neighborhood with the epsilon as the radius of the point o exceeds a given threshold MinPts, the point o is marked as a core point; points which are not core points but fall in the neighborhood of a certain core point are marked as boundary points; any point that is neither a core point nor a boundary point is a noise point. Wherein the neighborhood radius ε and the density threshold MinPts are specified by the user;
step 2: deleting all noise points;
and step 3: two core points having a distance smaller than the neighborhood radius epsilon are connected to form a new cluster.
And 4, step 4: the recorded data at each moment is given a cluster class label, namely corresponding to a safety state of the monitored object.
The method is characterized in that: the method for establishing the multi-classification prediction model by adopting the SVM classification algorithm comprises the following steps:
step 1: and aiming at the data corresponding to each class label, marking the points belonging to the class as positive examples, marking the points not belonging to the class as negative examples, and training a classifier aiming at the class by using the marked data through an SVM algorithm so as to distinguish whether the data belong to the class or not.
Step 2: classifying the newly generated monitoring data by using a classifier corresponding to each safety state respectively, integrating classification results of all the classifiers, and judging the safety state of the monitoring data to be the class when one and only one classifier divides the monitoring data into the corresponding states; otherwise, if there is no classifier or the classifiers classify the data into the corresponding states, the safety state of the monitored data is determined as the outlier.
Fig. 1 shows a system configuration of the present invention.
The method comprises the following steps:
step 1: acquiring running state data of the numerical control machine tool by adopting a development interface provided by a numerical control manufacturer or an OPC protocol mode, wherein the running state data comprises six parameters of spindle motor temperature, spindle current, spindle motor load, spindle rotation error, X-axis motor temperature and X-axis actual speed;
step 2: because the attribute value and the threshold value of each feature are different, the data normalization processing needs to be carried out on the data set, and the standard of the data normalization adopts a z-score normalization method;
and step 3: producing the theme by using Kafka to create topic, and sending the theme to Spark Streaming consumption;
and 4, step 4: preprocessing the implementation state monitoring data by using a Spark streaming real-time data calculation framework of Spark, namely defining continuous data sources of each Topic in Kafka as a data stream DStream in Spark Job, wherein each DStream is internally represented by a group of continuous RDDs, and then converting the operation of the DStream into the operation of the RDDs in Spark;
and 5: using a DBSCAN algorithm in Spark-MLib, setting a MinPts parameter and a neighborhood radius epsilon in the DBSCAN algorithm as proper values, and clustering data generated in different time periods in a data set into different clusters through the DBSCAN algorithm;
step 6: the data clusters are divided into a training set and a test set according to the proportion of 2:1 in an equidistant sampling mode, namely, the data clusters at the first two moments in every three adjacent moments are added into the training set, and the data clusters at the third moment are added into the test set. In the training process of the classifier corresponding to each state, regarding the data in the training set and the test set, the data belonging to the class is marked as a positive example, and the data not belonging to the class is marked as a negative example. And respectively calling a training algorithm provided in the Spark-MLib-SVM aiming at each safety state, obtaining a classifier corresponding to the state based on a training set, and sequentially verifying the accuracy of the generated classifier through a test set.
Claims (8)
1. A Spark-based method for monitoring the running state of a numerical control machine is characterized by comprising the following steps:
step 1: collecting state data information of the numerical control machine tool;
step 2: then, carrying out normalization processing on the state data information to obtain state data;
and step 3: kafka accesses state data, different types of state data are integrated by adding a Topic field into the data, the data of the same Topic are partitioned to different servers according to a set algorithm, and a stream computing system spark streaming computes the data;
and 4, step 4: preprocessing the state data by using Spark streaming of Spark to obtain a state data sample;
and 5: taking a state data sample as input, dividing a monitored object into different safety states as output, and establishing a multi-classification prediction model; and predicting the monitoring data to be detected through a multi-classification prediction model.
2. The Spark-based numerical control machine tool operation state monitoring method according to claim 1, wherein: the acquisition is realized in one of two ways; the first mode is through the development interface of the numerical control machine tool, and the other mode is through the OPC protocol acquisition.
3. The Spark-based numerical control machine tool operation state monitoring method according to claim 1, wherein: the state data information comprises spindle motor temperature, spindle current, spindle motor load, spindle rotation error, X-axis motor temperature and feeding speed.
4. The Spark-based numerical control machine tool operation state monitoring method according to claim 1, wherein: the preprocessing of the state data by using Spark streaming is specifically as follows:
in Spark Job of Spark, data of each Topic in Kafka is defined as a data stream DStream, and each DStream is internally represented by a set of consecutive RDDs.
5. The Spark-based numerical control machine tool operation state monitoring method according to claim 1, wherein: the method for establishing the multi-classification prediction model by using the state data samples as input and the monitoring objects divided into different safety states as output comprises the following steps:
clustering data generated in different time periods in a data set into different clusters by training labeled state data samples and using a density-based clustering algorithm DBSCAN, thereby finding different safe operation states of a machine tool, and dividing a monitored object into different safe states according to a clustering result;
and establishing a multi-classification prediction model by adopting an SVM classification algorithm aiming at different safety states.
6. The Spark-based numerical control machine tool operation state monitoring method according to claim 5, wherein: the clustering algorithm DBSCAN based on density is as follows:
1) classifying core points, boundary points and noise points according to the density based on the center: if the number of points contained in the neighborhood with the epsilon as the radius of the point o exceeds a given threshold value MinPts, the point o is marked as a core point; points which are not core points but fall in the neighborhood of a certain core point are marked as boundary points; any point that is neither a core point nor a boundary point is a noise point;
2) deleting all noise points;
3) connecting two core points with the distance smaller than the neighborhood radius epsilon to form a new cluster;
4) the recorded data at each moment is given a cluster class label, namely corresponding to a safety state of the monitored object.
7. The Spark-based numerical control machine tool operation state monitoring method according to claim 5, wherein: the method for establishing the multi-classification prediction model by adopting the SVM classification algorithm comprises the following steps:
and for the data corresponding to each class label, marking the points belonging to the class as positive examples, marking the points not belonging to the class as negative examples, and training a classifier for the class by using the marked data through an SVM algorithm.
8. The Spark-based numerical control machine tool operation state monitoring method according to claim 1, wherein: the prediction of the monitoring data to be detected through the multi-classification prediction model is as follows: classifying the newly generated monitoring data by using a classifier corresponding to each safety state respectively, integrating classification results of all the classifiers, and judging the safety state of the monitoring data to be the class when one and only one classifier divides the monitoring data into the corresponding states; otherwise, if there is no classifier or the classifiers classify the data into the corresponding states, the safety state of the monitored data is determined as the outlier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811472641.1A CN111273607B (en) | 2018-12-04 | 2018-12-04 | Spark-based numerical control machine tool running state monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811472641.1A CN111273607B (en) | 2018-12-04 | 2018-12-04 | Spark-based numerical control machine tool running state monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111273607A true CN111273607A (en) | 2020-06-12 |
| CN111273607B CN111273607B (en) | 2022-12-13 |
Family
ID=70998500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811472641.1A Active CN111273607B (en) | 2018-12-04 | 2018-12-04 | Spark-based numerical control machine tool running state monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111273607B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505119A (en) * | 2021-07-29 | 2021-10-15 | 青岛以萨数据技术有限公司 | ETL method and device based on multiple data sources |
| CN114429240A (en) * | 2021-12-21 | 2022-05-03 | 浙江永基智能科技有限公司 | Method and device for monitoring running state of highway equipment |
| CN115049028A (en) * | 2022-08-17 | 2022-09-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN116912241A (en) * | 2023-09-12 | 2023-10-20 | 深圳市艾为创科技有限公司 | CNC machine adjustment optimization method and system based on machine learning |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| US20160239857A1 (en) * | 2013-01-04 | 2016-08-18 | PlaceIQ, Inc. | Inferring consumer affinities based on shopping behaviors with unsupervised machine learning models |
| CN106649809A (en) * | 2016-12-29 | 2017-05-10 | 苏碧云 | Internet of Things analysis method |
| CN106844585A (en) * | 2017-01-10 | 2017-06-13 | 广东精规划信息科技股份有限公司 | A kind of time-space relationship analysis system based on multi-source Internet of Things location aware |
| CN106844161A (en) * | 2017-02-20 | 2017-06-13 | 重庆邮电大学 | Abnormal monitoring and Forecasting Methodology and system in a kind of carrier state stream calculation system |
| US20170286838A1 (en) * | 2016-03-29 | 2017-10-05 | International Business Machines Corporation | Predicting solar power generation using semi-supervised learning |
| US20170316342A1 (en) * | 2016-05-02 | 2017-11-02 | Cisco Technology, Inc. | Refined learning data representation for classifiers |
| CN107480699A (en) * | 2017-07-13 | 2017-12-15 | 电子科技大学 | A kind of intrusion detection method based on channel condition information and SVMs |
| CN107846472A (en) * | 2017-11-24 | 2018-03-27 | 华北电力大学（保定） | The fleet anomaly detection method of extensive power transmission and transforming equipment Monitoring data flow |
| CN108062555A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Monitoring data early warning system based on Spark streamings cluster |
| CN108718345A (en) * | 2018-09-05 | 2018-10-30 | 电子科技大学 | A kind of digitlization workshop industrial data Network Transmitting system |
| CN108803486A (en) * | 2018-08-16 | 2018-11-13 | 重庆理工大学 | Numerical control machining tool heat error prediction based on deep learning network in parallel and compensation method |
-
2018
- 2018-12-04 CN CN201811472641.1A patent/CN111273607B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160239857A1 (en) * | 2013-01-04 | 2016-08-18 | PlaceIQ, Inc. | Inferring consumer affinities based on shopping behaviors with unsupervised machine learning models |
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| US20170286838A1 (en) * | 2016-03-29 | 2017-10-05 | International Business Machines Corporation | Predicting solar power generation using semi-supervised learning |
| US20170316342A1 (en) * | 2016-05-02 | 2017-11-02 | Cisco Technology, Inc. | Refined learning data representation for classifiers |
| CN108062555A (en) * | 2016-11-08 | 2018-05-22 | 南京理工大学 | Monitoring data early warning system based on Spark streamings cluster |
| CN106649809A (en) * | 2016-12-29 | 2017-05-10 | 苏碧云 | Internet of Things analysis method |
| CN106844585A (en) * | 2017-01-10 | 2017-06-13 | 广东精规划信息科技股份有限公司 | A kind of time-space relationship analysis system based on multi-source Internet of Things location aware |
| CN106844161A (en) * | 2017-02-20 | 2017-06-13 | 重庆邮电大学 | Abnormal monitoring and Forecasting Methodology and system in a kind of carrier state stream calculation system |
| CN107480699A (en) * | 2017-07-13 | 2017-12-15 | 电子科技大学 | A kind of intrusion detection method based on channel condition information and SVMs |
| CN107846472A (en) * | 2017-11-24 | 2018-03-27 | 华北电力大学（保定） | The fleet anomaly detection method of extensive power transmission and transforming equipment Monitoring data flow |
| CN108803486A (en) * | 2018-08-16 | 2018-11-13 | 重庆理工大学 | Numerical control machining tool heat error prediction based on deep learning network in parallel and compensation method |
| CN108718345A (en) * | 2018-09-05 | 2018-10-30 | 电子科技大学 | A kind of digitlization workshop industrial data Network Transmitting system |
Non-Patent Citations (2)
| Title |
|---|
| 吴奔等: "基于流计算的电力调度网络流量监测平台", 《计算机系统应用》 * |
| 李海等: "基于多维时间序列的数控机床状态预测方法研究", 《工程科学与技术》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113505119A (en) * | 2021-07-29 | 2021-10-15 | 青岛以萨数据技术有限公司 | ETL method and device based on multiple data sources |
| CN113505119B (en) * | 2021-07-29 | 2023-08-29 | 青岛以萨数据技术有限公司 | ETL method and device based on multiple data sources |
| CN114429240A (en) * | 2021-12-21 | 2022-05-03 | 浙江永基智能科技有限公司 | Method and device for monitoring running state of highway equipment |
| CN115049028A (en) * | 2022-08-17 | 2022-09-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN115049028B (en) * | 2022-08-17 | 2022-12-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN116912241A (en) * | 2023-09-12 | 2023-10-20 | 深圳市艾为创科技有限公司 | CNC machine adjustment optimization method and system based on machine learning |
| CN116912241B (en) * | 2023-09-12 | 2023-12-12 | 深圳市艾为创科技有限公司 | CNC machine adjustment optimization method and system based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111273607B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111273607B (en) | Spark-based numerical control machine tool running state monitoring method | |
| CN110347116B (en) | Machine tool state monitoring system and monitoring method based on operation data flow | |
| CN106844161B (en) | Abnormity monitoring and predicting method and system in calculation system with state flow | |
| CN107577588B (en) | Intelligent operation and maintenance system for mass log data | |
| CN110032557B (en) | Power grid equipment state abnormity monitoring method and system based on big data | |
| CN110059442A (en) | A kind of turnery processing cutter replacing method based on Part Surface Roughness and power information | |
| US11644812B2 (en) | Machine tool management method, machine tool management system and medium | |
| CN112699113B (en) | Industrial manufacturing process operation monitoring system driven by time sequence data stream | |
| Ritou et al. | Knowledge-based multi-level aggregation for decision aid in the machining industry | |
| US20220179393A1 (en) | Machine tool evaluation method, machine tool evaluation system and medium | |
| CN109494757B (en) | Voltage reactive power operation early warning method and system | |
| Li et al. | Tool breakage detection using deep learning | |
| CN115996249A (en) | Data transmission method and device based on grading | |
| CN112858901A (en) | System and method for monitoring operation state and service life prediction of cutter in real time | |
| WO2024007580A1 (en) | Power equipment parallel fault diagnosis method and apparatus based on hybrid clustering | |
| CN113535422A (en) | Cloud platform system for data cleaning and event processing of industrial big data | |
| Zhou et al. | Abnormal data processing of wind turbine based on combined algorithm and class center imputation | |
| Wu | RETRACTED: Research on Clustering Algorithm Based on Big Data Background | |
| CN115391429A (en) | Time sequence data processing method and device based on big data cloud computing | |
| CN112069633B (en) | Power distribution network data preprocessing method based on particle swarm principle and adopting big data clustering | |
| CN111813631A (en) | Resource situation visualization and analysis method for cloud data center | |
| CN111259000A (en) | Data cleaning method | |
| Wu et al. | Intelligent service platform of manufacturing process and tool based on data warehouse | |
| CN114328513A (en) | Big data attribute importance and identification degree early warning method based on clustering | |
| Diao et al. | An improved DBSCAN algorithm using local parameters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No. 16-2, Nanping East Road, Dongling District, Shenyang City, Liaoning Province, 110168 Patentee after: Shenyang Zhongke CNC Technology Co.,Ltd. Address before: No. 16-2, Nanping East Road, Dongling District, Shenyang City, Liaoning Province, 110168 Patentee before: Shenyang Golding Nc Intelligence Tech.co.,ltd. |
|
| CP01 | Change in the name or title of a patent holder |